© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62006
    Prev
    Next
    INDEX
    Explanations

    facilitation tips and notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     F
    0.70
    f
    0.52
    int
    0.52
     Fuck
    0.51
    ার
    0.50
    ak
    0.49
    arus
    0.46
     ಇ
    0.44
    αν
    0.44
     Phelps
    0.44
    POSITIVE LOGITS
    两天
    0.64
    days
    0.58
    තිය
    0.55
     минуты
    0.55
    두
    0.55
     gấp
    0.54
    两
    0.54
     days
    0.54
    兩
    0.52
    这位
    0.52
    Activations Density 0.030%

    No Known Activations